Every run: the agent's full trajectory, its submissions over the 20-hour budget, and the final score.
| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 | 0.6214 | $15.11 | 24.2M | 125k | 16h 58m | 204 | 11 |
| 2 | Claude Fable 5.1 | 0.6178 | $12.69 | 20.4M | 104k | 18h 1m | 175 | 12 |
| 3 | Claude Fable 5.1 | 0.6011 | $16.81 | 27.4M | 129k | 16h 5m | 208 | 16 |
| 4 | Claude Fable 5.1 | 0.5960 | $16.06 | 25.6M | 135k | 16h 36m | 193 | 12 |
| 5 | GPT-5.6 | 0.5936 | $28.82 | 47.8M | 113k | 15h 13m | 294 | 4 |
| 6 | GLM-5.3 | 0.5873 | $22.61 | 71.9M | 228k | 18h 20m | 314 | 2 |
| 7 | Grok 4.6 | 0.5804 | $120.40 | 104.0M | 444k | 19h 13m | 464 | 37 |
| 8 | Gemini 3.7 Flash | 0.5747 | $22.40 | 49.9M | 145k | 13h 34m | 256 | 7 |
| 9 | Gemini 3.7 Flash | 0.5566 | $16.56 | 54.7M | 160k | 9h 58m | 285 | 2 |
| 10 | Grok 4.6 | 0.5522 | $208.02 | 184.0M | 911k | 19h 55m | 826 | 53 |
| 11 | Grok 4.6 | 0.5495 | $238.57 | 230.6M | 626k | 20h 0m | 861 | 62 |
| 12 | Gemini 3.7 Flash | 0.5365 | $13.11 | 37.7M | 147k | 6h 21m | 241 | 3 |
| 13 | Gemini 3.7 Flash | 0.5356 | $19.36 | 48.1M | 172k | 8h 5m | 252 | 4 |
| 14 | Gemini 3.7 Flash | 0.5332 | $4.99 | 21.4M | 136k | 4h 20m | 171 | 1 |
| 15 | GLM-5.3 | 0.4818 | $19.75 | 47.5M | 201k | 18h 1m | 273 | 5 |
| 16 | GLM-5.3 | 0.4745 | $28.03 | 96.3M | 327k | 19h 20m | 363 | 7 |
| 17 | GLM-5.3 | 0.4723 | $21.03 | 47.8M | 206k | 18h 36m | 293 | 2 |
| 18 | GLM-5.3 | 0.4679 | $26.30 | 77.9M | 252k | 19h 29m | 364 | 2 |
| 19 | DeepSeek V4 Flash Vision Exp | 0.4639 | $1.55 | 83.0M | 253k | 19h 5m | 403 | 5 |
| 20 | Grok 4.6 | 0.4530 | $43.07 | 35.9M | 245k | 19h 35m | 225 | 1 |
| 21 | Grok 4.6 | 0.4154 | $92.48 | 66.7M | 263k | 19h 27m | 303 | 6 |
| 22 | Qwen3.8-Max | 0.4005 | $8.94 | 29.1M | 230k | 19h 22m | 281 | 1 |
| 23 | Qwen3.8-Max | 0.3989 | $14.91 | 48.7M | 387k | 19h 25m | 357 | 1 |
| 24 | Qwen3.8-Max | 0.3606 | $13.12 | 44.7M | 268k | 19h 18m | 385 | 3 |
| 25 | Muse Spark 1.2 | 0.3456 | $4.38 | 18.4M | 145k | 37m | 104 | 2 |
| 26 | Qwen3.8-Max | 0.3410 | $4.91 | 14.6M | 172k | 18h 25m | 189 | 4 |
| 27 | Qwen3.8-Max | 0.3360 | $8.01 | 25.7M | 213k | 18h 56m | 239 | 8 |
| 28 | Muse Spark 1.2 | 0.3227 | $38.37 | 235.4M | 385k | 2h 26m | 592 | 5 |
| 29 | Muse Spark 1.2 | 0.3018 | $11.62 | 45.2M | 202k | 1h 9m | 181 | 7 |
| 30 | Muse Spark 1.2 | 0.2944 | $2.12 | 8.7M | 99k | 50m | 86 | 1 |
| 31 | Muse Spark 1.2 | 0.2758 | $11.17 | 51.5M | 378k | 2h 40m | 211 | 6 |
| 32 | Inkling | 0.2568 | $3.54 | 3.6M | 37k | 1h 43m | 97 | 1 |
| 33 | Inkling | 0.2237 | $3.91 | 3.9M | 47k | 1h 43m | 120 | 1 |
| 34 | Inkling | 0.1542 | $5.24 | 5.4M | 39k | 1h 50m | 132 | 2 |
| 35 | Inkling | 0.1482 | $3.49 | 3.6M | 19k | 1h 32m | 102 | 1 |
| 36 | GPT-5.6 | 0.0000 | $122.35 | 137.1M | 209k | 17h 41m | 576 | 7 |
| 37 | Kimi K3 | 0.0000 | $20.25 | 49.9M | 257k | 19h 31m | 296 | 8 |
| 38 | Kimi K3 | 0.0000 | $16.03 | 42.3M | 172k | 19h 35m | 282 | 1 |
| 39 | Kimi K3 | 0.0000 | $13.29 | 32.3M | 193k | 19h 22m | 245 | 2 |
| 40 | Inkling | 0.0000 | $6.20 | 6.2M | 72k | 38m | 132 | 1 |
| 41 | DeepSeek V4 Flash Vision Exp | 0.0000 | $1.66 | 90.1M | 258k | 19h 29m | 392 | 3 |
| 42 | DeepSeek V4 Flash Vision Exp | 0.0000 | $1.99 | 110.4M | 289k | 18h 13m | 487 | 4 |
| 43 | DeepSeek V4 Flash Vision Exp | 0.0000 | $1.55 | 84.2M | 243k | 18h 42m | 398 | 5 |
| 44 | GPT-5.6 | 0.0000 | $63.62 | 70.4M | 130k | 17h 56m | 290 | 3 |
| 45 | Kimi K3 | 0.0000 | $11.04 | 28.1M | 135k | 19h 31m | 261 | 6 |
| 46 | GPT-5.6 | 0.0000 | $72.57 | 94.1M | 189k | 15h 53m | 478 | 14 |
| 47 | DeepSeek V4 Flash Vision Exp | 0.0000 | $1.68 | 93.8M | 242k | 19h 27m | 452 | 2 |
| 48 | Claude Fable 5.1 | 0.0000 | $14.60 | 23.4M | 121k | 14h 28m | 186 | 8 |
| 49 | GPT-5.6 | 0.0000 | $88.96 | 100.2M | 138k | 14h 52m | 416 | 8 |
| 50 | Kimi K3 | 0.0000 | $19.09 | 48.5M | 196k | 18h 52m | 326 | 6 |